{
  "abstract": "Existing long-term power load forecasting models face significant challenges due to the complexity of non-stationary electricity data, inadequate information representation, and suboptimal prediction accuracy. To address these issues, this study introduces PowerNet, a novel forecasting framework based on a multi-period and multi-scale approach. PowerNet first employs Fast Fourier Transform (FFT) to perform multi-period analysis, transforming one-dimensional time series data into two-dimensional (2D) tensors to capture latent periodic patterns. A multi-scale information representation module is then implemented using computer vision-inspired techniques, including Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and non-local attention mechanisms to extract robust features from these tensors. Finally, a fully connected layer performs feature reconstruction, while residual connections facilitate multi-step load forecasting. PowerNet was evaluated against state-of-the-art models such as Informer, LogTrans, and ETSformer across two public electricity datasets and one weather dataset. At prediction horizons of 96, 192, 336, and 720 time steps, experimental results demonstrate that PowerNet achieves competitive or superior accuracy on the evaluated datasets. Notably, compared with Autoformer, PowerNet reduces the Mean Absolute Error (MAE) by 18.77% to 37.41% and the Mean Square Error (MSE) by 18.23% to 47.74%, significantly enhancing the reliability of long-term electricity load forecasting.",
  "abstract_shown": true,
  "affiliations": [
    "School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, Jilin, China.",
    "Yahe School of Design and Engineering, Haikou University of Economics, Haikou, Hainan, China.",
    "Tsinghua University, Beijing, China.",
    "Beijing Jiaotong University, Beijing, China."
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Xiaolin Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "Zhi Liu",
      "orcid": "0009-0002-0259-6605"
    },
    {
      "affs": [
        1
      ],
      "name": "Chunyang Wang"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Zhen Qian"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a83e5xgeb63js.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0361106",
  "fulltext_url": "https://europepmc.org/articles/PMC13722309",
  "id": "a83e5xgeb63js",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0361106",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Artificial Intelligence"
    ],
    [
      "heading",
      "Biology and Life Sciences"
    ],
    [
      "heading",
      "Computer Architecture"
    ],
    [
      "heading",
      "Computer and Information Sciences"
    ],
    [
      "heading",
      "Deep Learning"
    ],
    [
      "heading",
      "Electricity"
    ],
    [
      "heading",
      "Fast Fourier transforms"
    ],
    [
      "heading",
      "Forecasting"
    ],
    [
      "heading",
      "Fourier analysis"
    ],
    [
      "heading",
      "Machine Learning"
    ],
    [
      "heading",
      "Mathematical Functions"
    ],
    [
      "heading",
      "Mathematical and Statistical Techniques"
    ],
    [
      "heading",
      "Mathematical and statistical techniques"
    ],
    [
      "heading",
      "Mathematics"
    ],
    [
      "heading",
      "Neural Networks"
    ],
    [
      "heading",
      "Neuroscience"
    ],
    [
      "heading",
      "Physical Sciences"
    ],
    [
      "heading",
      "Physics"
    ],
    [
      "heading",
      "Recurrent Neural Networks"
    ],
    [
      "heading",
      "Research Article"
    ],
    [
      "heading",
      "Research and Analysis Methods"
    ],
    [
      "heading",
      "Research and analysis methods"
    ],
    [
      "heading",
      "Statistical Methods"
    ],
    [
      "heading",
      "Statistics"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Neural networks/Recurrent neural networks"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Deep learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Computer architecture"
    ],
    [
      "plos",
      "/Computer and information sciences/Neural networks/Recurrent neural networks"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Statistics/Statistical methods/Forecasting"
    ],
    [
      "plos",
      "/Physical sciences/Physics/Electricity"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Fourier analysis/Fast Fourier transforms"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Mathematical functions"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Statistical methods/Forecasting"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://europepmc.org/articles/PMC13722309?pdf=render",
  "pmcid": "PMC13722309",
  "pmid": "42961959",
  "published": "2026-10-30",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/a83e5xgeb63js.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T12:20:55Z",
      "native_id": "10.1371/journal.pone.0361106",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0361106"
    },
    {
      "first_seen": "2026-11-02T03:21:21Z",
      "native_id": "MED:42961959",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42961959"
    },
    {
      "first_seen": "2026-11-03T12:22:50Z",
      "native_id": "PMC13722309",
      "source": "pmc",
      "url": "https://doi.org/10.1371/journal.pone.0361106"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    },
    {
      "field": "mathematics",
      "origin": "plos:statistical methods",
      "subfield": "statistics"
    },
    {
      "field": "physics",
      "origin": "heading:Physics",
      "subfield": "general"
    }
  ],
  "title": "Long-term electricity load forecasting model based on multi-period and multi-scale analysis",
  "title_text": "Long-term electricity load forecasting model based on multi-period and multi-scale analysis",
  "type": "peer-reviewed",
  "updated_at": "2026-11-03T12:22:50Z",
  "url": "https://research.draconitic.com/paper/a83e5xgeb63js",
  "venue": "PLOS One",
  "versions": []
}